{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:T4HD7RGAMDXLFP6YCG5VGHKUYY","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"58560f6e7a9c2e2cca50ad7d25a1547a43029aaa41cc9c5723add94232ffe862","cross_cats_sorted":["cs.AI","math.RA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-23T05:55:52Z","title_canon_sha256":"feed14295d552fef19e547aaa5c0248c6852af8b588d8875faa02f59a6fabbe1"},"schema_version":"1.0","source":{"id":"2602.19533","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.19533","created_at":"2026-05-17T23:39:15Z"},{"alias_kind":"arxiv_version","alias_value":"2602.19533v2","created_at":"2026-05-17T23:39:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.19533","created_at":"2026-05-17T23:39:15Z"},{"alias_kind":"pith_short_12","alias_value":"T4HD7RGAMDXL","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"T4HD7RGAMDXLFP6Y","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"T4HD7RGA","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:2305eb6b96e92efb74c5810ffb20c89d9539f2b3feca1fe9f9cdf1017b53c251","target":"graph","created_at":"2026-05-17T23:39:15Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Learning multiplication in finite-dimensional algebras amounts to learning a bilinear product specified by the algebra's structure tensor, and grokking emerges naturally as models learn discrete representations for algebras over finite fields."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the experimental models are actually learning the algebra's multiplication via the structure tensor rather than some other shortcut that happens to correlate with the target operation."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Neural networks learning multiplication in finite-dimensional algebras show grokking whose timing depends on algebraic properties like commutativity and the rank/sparsity of the structure tensor."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Neural networks grok algebra multiplication once they recover the bilinear product from the structure tensor."}],"snapshot_sha256":"4707ba5ff95829468742a284349410ef5f18f7b6da3bcf3d27b40ebcf879d145"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"bd224ddaa0b5a28cbea69a2887510e6e0aabfdf7a83c74ab7c9ac0b4c12da1f8"},"paper":{"abstract_excerpt":"This paper investigates the grokking phenomenon, which refers to the sudden transition from a long memorization to generalization observed during neural networks training, in the context of learning multiplication in finite-dimensional algebras (FDA). While prior work on grokking has focused mainly on group operations, we extend the analysis to more general algebraic structures, including non-associative, non-commutative, and non-unital algebras. We show that learning group operations is a special case of learning FDA, and that learning multiplication in FDA amounts to learning a bilinear prod","authors_text":"Guillaume Dumas, Guillaume Rabusseau, Pascal Jr Tikeng Notsawo","cross_cats":["cs.AI","math.RA"],"headline":"Neural networks grok algebra multiplication once they recover the bilinear product from the structure tensor.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-23T05:55:52Z","title":"Grokking Finite-Dimensional Algebra"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.19533","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-15T20:19:51.927536Z","id":"89ef4905-57d0-48a7-b620-e0b095c76281","model_set":{"reader":"grok-4.3"},"one_line_summary":"Neural networks learning multiplication in finite-dimensional algebras show grokking whose timing depends on algebraic properties like commutativity and the rank/sparsity of the structure tensor.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Neural networks grok algebra multiplication once they recover the bilinear product from the structure tensor.","strongest_claim":"Learning multiplication in finite-dimensional algebras amounts to learning a bilinear product specified by the algebra's structure tensor, and grokking emerges naturally as models learn discrete representations for algebras over finite fields.","weakest_assumption":"That the experimental models are actually learning the algebra's multiplication via the structure tensor rather than some other shortcut that happens to correlate with the target operation."}},"verdict_id":"89ef4905-57d0-48a7-b620-e0b095c76281"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:050d2cfc16d2e34d5d1c58d956cea21fe0e0b421b8b9406629a74db46a68ba3a","target":"record","created_at":"2026-05-17T23:39:15Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"58560f6e7a9c2e2cca50ad7d25a1547a43029aaa41cc9c5723add94232ffe862","cross_cats_sorted":["cs.AI","math.RA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-23T05:55:52Z","title_canon_sha256":"feed14295d552fef19e547aaa5c0248c6852af8b588d8875faa02f59a6fabbe1"},"schema_version":"1.0","source":{"id":"2602.19533","kind":"arxiv","version":2}},"canonical_sha256":"9f0e3fc4c060eeb2bfd811bb531d54c60b5fd151f776a6801ae661123109ddf4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9f0e3fc4c060eeb2bfd811bb531d54c60b5fd151f776a6801ae661123109ddf4","first_computed_at":"2026-05-17T23:39:15.997675Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:39:15.997675Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VSkwPdMR81k0kyP+O0ZTwdQlo6bsGw8NcXAJDb0wk6bbDzz+UNT8+5+48MFAc466pNep8DD28Uj1w460NrbnDw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:39:15.998563Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.19533","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:050d2cfc16d2e34d5d1c58d956cea21fe0e0b421b8b9406629a74db46a68ba3a","sha256:2305eb6b96e92efb74c5810ffb20c89d9539f2b3feca1fe9f9cdf1017b53c251"],"state_sha256":"959865c82b2f16c202fc64f8120bb74f0827112bcb8d7318437b369f1f66c263"}